KNELPerf v2 wave 1: Ultix scheduler breakout + loop skeleton + reports (#826)
ci / audit (push) Failing after 26s

- scheduler/: day/night engine (conf-driven redesign), psi/perfsnap collectors,
  proxmox-ctl, systemd timer templates — ported from ~/projects/ultix per the
  breakout map in scheduler/README.md
- loop/: perf-loop driver (baseline/audit/tweak/rebaseline), cpu-bench (new CPU
  leg), baseline-diff (tolerance compare) — smoke-tested locally
- docs/ARCHITECTURE.md: full program design (loop, resource groups, VM/spindle
  balancing, k8s-vs-Slurm, beszel+RAPL/iDRAC telemetry spine, workload classes,
  solar/HA + two-site power economics)
- docs/report-amt-power-telemetry.md + docs/report-moonlight-desktop.md

Redmine: https://projects.knownelement.com/issues/826#note-2
This commit is contained in:
2026-09-06 14:16:54 -05:00
parent 89a93359f0
commit 25299373f7
19 changed files with 839 additions and 1 deletions
+35
View File
@@ -0,0 +1,35 @@
#!/usr/bin/env bash
# KNELPerf baseline diff — compares two baseline bundles (or live-audits one).
#
# baseline-diff.sh <dirA> <dirB> compare two stored bundles
# Values are TSV metric/value/unit rows from cpu-bench.tsv. Numeric metrics
# compare with a tolerance (default 10%); non-numeric metrics compare for
# equality (governor flips are exactly what we want to catch).
set -euo pipefail
TOL_PCT=${KNELPERF_DIFF_TOL:-25} # 1-thread openssl on a busy host swings >10% run-to-run
[ $# = 2 ] || { echo "usage: $0 <dirA> <dirB>" >&2; exit 2; }
A=$1; B=$2
[ -r "$A/cpu-bench.tsv" ] || { echo "no cpu-bench.tsv in $A" >&2; exit 3; }
[ -r "$B/cpu-bench.tsv" ] || { echo "no cpu-bench.tsv in $B" >&2; exit 3; }
join_tsv() { awk -F'\t' 'NR==FNR{a[$1]=$2;next} {print $1"\t"a[$1]"\t"$2"\t"$3}' "$1" "$2"; }
# shellcheck disable=SC2034 # exit-status reserved for future strictness
status=0
join_tsv "$A/cpu-bench.tsv" "$B/cpu-bench.tsv" | while IFS=$'\t' read -r metric va vb unit; do
[ -n "$va" ] && [ -n "$vb" ] || continue
if [ "$va" = "$vb" ]; then
printf 'OK %-28s %s = %s %s\n' "$metric" "$va" "$vb" "$unit"
elif [ "$va" = "${va#[-+0-9.]}" ] || [ "$vb" = "${vb#[-+0-9.]}" ]; then
printf 'DRIFT %-28s %s -> %s %s\n' "$metric" "$va" "$vb" "$unit"
else
delta=$(awk -v a="$va" -v b="$vb" 'BEGIN{d=(b-a)/((a==0)?1:a)*100; printf "%+.1f", d}')
flag=$(awk -v d="${delta#+}" -v t="$TOL_PCT" 'BEGIN{m=d<0?-d:d; if(m>t) print "DELTA"; else print "OK"}')
if [ "$flag" = OK ]; then
printf 'OK %-28s %s -> %s (%s%%) %s\n' "$metric" "$va" "$vb" "$delta" "$unit"
else
printf 'DELTA %-28s %s -> %s (%s%%) %s\n' "$metric" "$va" "$vb" "$delta" "$unit"
fi
fi
done
echo "tolerance: ${TOL_PCT}% (set KNELPERF_DIFF_TOL to change)"
+51
View File
@@ -0,0 +1,51 @@
#!/usr/bin/env bash
# KNELPerf CPU benchmark — the missing CPU leg of the perf loop (#826).
# Runs ON the target host (or locally). Zero-install friendly: uses openssl
# (always present) plus sysbench when available. Output = TSV tag/value.
#
# Design notes:
# - openssl speed = single+multi core crypto throughput (stable, comparable)
# - sysbench cpu (if installed) = integer event rate
# - /proc-derived context: governor, PSI at capture time
set -u
DUR=${KNELPERF_CPUBENCH_SECS:-10}
echo -e "metric\tvalue\tunit"
gov=$(cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor 2>/dev/null || echo none)
echo -e "governor\t$gov\t-"
nproc=$(nproc)
echo -e "nproc\t$nproc\t-"
# openssl: 1 thread then all threads, aes-256-cbc (avx-sensitive) and sha256.
# Parse: LAST line whose first field is the algo; value = last numeric field
# (per-thread rows precede the aggregate row in -multi output).
for algo in aes-256-cbc sha256; do
v=$(openssl speed -seconds "$DUR" "$algo" 2>/dev/null \
| awk -v a="$algo" '$1==a{v=$NF} END{print v}')
[ -n "${v:-}" ] && echo -e "openssl_${algo}_1t\t$v\tk/s"
# -multi: per-thread rows precede the aggregate; keep the LAST match
v=$(openssl speed -multi "$nproc" -seconds "$DUR" "$algo" 2>/dev/null \
| awk -v a="$algo" '$1==a{v=$NF} END{print v}')
[ -n "${v:-}" ] && echo -e "openssl_${algo}_${nproc}t\t$v\tk/s"
done
# sysbench (optional, if installed)
if command -v sysbench >/dev/null 2>&1; then
ev=$(sysbench cpu --time=$((DUR*1000)) --threads=1 run 2>/dev/null \
| awk -F'/s|events per second:/{for(i=1;i<=NF;i++) if($i ~ /^[0-9.]+$/){print $i; exit}}')
[ -n "${ev:-}" ] && echo -e "sysbench_cpu_1t\t$ev\tevents/s"
ev=$(sysbench cpu --time=$((DUR*1000)) --threads="$nproc" run 2>/dev/null \
| awk -F'/s|events per second:/{for(i=1;i<=NF;i++) if($i ~ /^[0-9.]+$/){print $i; exit}}')
[ -n "${ev:-}" ] && echo -e "sysbench_cpu_${nproc}t\t$ev\tevents/s"
else
echo -e "sysbench_cpu\tabsent\t-"
fi
# PSI snapshot at capture time (context for the numbers above)
for res in cpu memory io; do
v=$(awk '$1=="some"{for(i=2;i<=NF;i++) if($i ~ /^avg60=/){sub("avg60=","",$i); print $i; exit}}' \
"/proc/pressure/$res" 2>/dev/null || echo 0)
echo -e "psi_${res}_avg60\t$v\t%"
done
exit 0
+65
View File
@@ -0,0 +1,65 @@
#!/usr/bin/env bash
# KNELPerf loop driver — baseline -> audit/benchmark -> tweak -> re-baseline.
#
# The heart of KNELPerf v2 (#826). One host, one cycle phase at a time:
#
# perf-loop.sh baseline <host> capture baseline bundle (cpu/net/storage/psi)
# perf-loop.sh audit <host> read-only audit vs baseline (alerts on drift)
# perf-loop.sh tweak <host> <id> apply a tweak (from tweaks/) after CR gate
# perf-loop.sh rebaseline <host> capture post-tweak bundle + diff report
# perf-loop.sh compare <host> <a> <b> diff two stored bundles
#
# Bundles live in data/baselines/<host>/<ts>/ and are plain TSV/JSON so diff
# and jq stay the toolchain. Nothing here mutates a host except `tweak`.
set -euo pipefail
REPO_ROOT=$(cd "$(dirname "$0")/.." && pwd)
DATA_DIR=${KNELPERF_DATA_DIR:-$REPO_ROOT/data/baselines}
SSH_OPTS=(-o ConnectTimeout=8 -o BatchMode=yes)
usage() { sed -n '2,12p' "$0"; exit 2; }
[ $# -ge 2 ] || usage
cmd=$1; host=$2
now() { date +%Y%m%d-%H%M%S; }
host_dir() { mkdir -p "$DATA_DIR/$1"; }
run_on_host() { # host script-path args...
local h=$1 script=$2; shift 2
case $h in
local) bash "$REPO_ROOT/$script" "$@" ;;
*) ssh "${SSH_OPTS[@]}" "root@$h" "bash -s" < "$REPO_ROOT/$script" "$@" ;;
esac
}
case "$cmd" in
baseline|rebaseline)
ts=$(now); dir="$DATA_DIR/$host/$ts"; host_dir "$host"; mkdir -p "$dir"
echo "== KNELPerf $cmd: $host -> $dir"
# shellcheck disable=SC2043 # single-part list by design; grows as legs are added
for part in cpu-bench; do
run_on_host "$host" "loop/$part.sh" > "$dir/$part.tsv" 2> "$dir/$part.err" \
|| echo "WARN: $part failed (see $dir/$part.err)"
done
# storage + network reuse the existing bench harness outputs
run_on_host "$host" "bench/bench-run.sh" > "$dir/bench-run.tsv" 2> "$dir/bench.err" \
|| echo "WARN: bench-run failed (see $dir/bench.err)"
echo "$cmd $host $ts" > "$dir/MANIFEST"
echo "done: $(ls "$dir")"
;;
audit)
latest=$(find "$DATA_DIR/$host" -maxdepth 1 -mindepth 1 -type d -printf '%f\n' 2>/dev/null | sort | tail -1)
[ -n "$latest" ] || { echo "no baseline for $host" >&2; exit 3; }
echo "== KNELPerf audit: $host vs baseline $latest"
"$REPO_ROOT/loop/baseline-diff.sh" "$DATA_DIR/$host/$latest" "$host"
;;
tweak)
[ $# -ge 3 ] || usage; tweak_id=$3
echo "== KNELPerf tweak $tweak_id on $host (CR gate applies - see AGENTS.md)"
run_on_host "$host" "tweaks/$tweak_id.sh"
;;
compare)
[ $# -ge 4 ] || usage
"$REPO_ROOT/loop/baseline-diff.sh" "$DATA_DIR/$host/$3" "$DATA_DIR/$host/$4"
;;
*) usage ;;
esac